Dual-Classifier Label Correction Network for Carotid Plaque Classification on Multi-Center Ultrasound Images

Carotid artery plaques represent a major contributor to the morbidity and mortality associated with cerebrovascular disease, and their clinical significance is largely determined by the risk linked to plaque vulnerability. Therefore, classifying plaque risk constitutes one of the most critical tasks in the clinical management of this condition. While classification models derived from individual medical centers have been extensively investigated, these single-center models often fail to generalize well to multi-center data due to variations in ultrasound images caused by differences in physician expertise and equipment. To address this limitation, a Dual-Classifier Label Correction Network model (DCLCN) is proposed for the classification of carotid plaque ultrasound images across multiple medical centers. The DCLCN designs a multi-center domain adaptation module that leverages a dual-classifier strategy to extract knowledge from both source and target centers, thereby reducing feature discrepancies through a domain adaptation layer. Additionally, to mitigate the impact of image noise, a label modeling and correction module is introduced to generate pseudo-labels for the target centers and iteratively refine them using an end-to-end correction mechanism. Experiments on the carotid plaque dataset collected from three medical centers demonstrate that the DCLCN achieves commendable performance and robustness.